fix api and salary estimator

app.py

@@ -145,7 +145,7 @@ async def predict(predictionFeatures: PredictionFeatures):
     years_experience = pd.DataFrame({"YearsExperience": [predictionFeatures.YearsExperience]})
 
     # Log model from mlflow 
-    logged_model = 'runs:/5e54b2ee620546b0914c9e9fbfd18875/salary_estimator'
+    logged_model = 'runs:/c09d09ef14e546b08f2f339d2c966da6/salary_estimator'
 
     # Load model as a PyFuncModel.
     loaded_model = mlflow.pyfunc.load_model(logged_model)

salary_predictor/docker/dockerfile

@@ -15,11 +15,6 @@ RUN ./aws/install
 COPY requirements.txt /dependencies/requirements.txt
 RUN pip install -r /dependencies/requirements.txt
 
-ENV AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID
-ENV AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY
-ENV BACKEND_STORE_URI=$BACKEND_STORE_URI
-ENV ARTIFACT_ROOT=$ARTIFACT_ROOT
-
 CMD mlflow server -p $PORT \
     --host 0.0.0.0 \
     --backend-store-uri $BACKEND_STORE_URI \

salary_predictor/docker/requirements.txt

@@ -2,7 +2,7 @@ boto3
 pandas 
 gunicorn 
 streamlit 
-sklearn 
+scikit-learn
 matplotlib 
 seaborn 
 plotly

salary_predictor/run.sh

@@ -4,7 +4,5 @@ docker run -it\
  -e PORT=4000\
  -e AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID\
  -e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY\
- -e BACKEND_STORE_URI=$BACKEND_STORE_URI\
- -e ARTIFACT_ROOT=$ARTIFACT_ROOT\
  -e MLFLOW_EXPERIMENT_NAME=$MLFLOW_EXPERIMENT_NAME\
- salary_estimator
+ salary_predictor python train.py